Analyses of swisscom data
API data
Data
Grid
Testing on several PLZs of Bern & surroundings.
bern_plz <- read_rds("data/grid/bern_plz.Rds") %>%
rename(tile_id = tileId)
bern_plz_ct <- st_centroid(bern_plz)x <character>
# total N=6965 valid N=6965 mean=3044.06 sd=37.39
Value | N | Raw % | Valid % | Cum. %
---------------------------------------
3005 | 198 | 2.84 | 2.84 | 2.84
3006 | 604 | 8.67 | 8.67 | 11.51
3007 | 254 | 3.65 | 3.65 | 15.16
3008 | 445 | 6.39 | 6.39 | 21.55
3010 | 28 | 0.40 | 0.40 | 21.95
3011 | 138 | 1.98 | 1.98 | 23.93
3012 | 581 | 8.34 | 8.34 | 32.28
3013 | 176 | 2.53 | 2.53 | 34.80
3014 | 366 | 5.25 | 5.25 | 40.06
3018 | 590 | 8.47 | 8.47 | 48.53
3027 | 720 | 10.34 | 10.34 | 58.87
3073 | 509 | 7.31 | 7.31 | 66.17
3074 | 389 | 5.59 | 5.59 | 71.76
3084 | 526 | 7.55 | 7.55 | 79.31
3095 | 152 | 2.18 | 2.18 | 81.49
3097 | 182 | 2.61 | 2.61 | 84.11
3098 | 1107 | 15.89 | 15.89 | 100.00
<NA> | 0 | 0.00 | <NA> | <NA>Dwell density
Data is from http://mip.swisscom.ch which swisscom describes as:
Our new API platform offering 3 endpoints focusing on density, dwell times and origin destination
Important note: free data is limited to 2020-01-27 only!
We are using Heatmaps
API to retrieve daily and hourly dwell times for one postcode. Code
to retrieve data, kindly provided by Yann Steimer from swisscom, is in
example_notebook_SC_heatmaps_API_UNIBE.ipynb.
Daily dwell density
read_fun <- function(filename) {
data <- readr::read_delim(filename,
delim = ";", escape_double = FALSE, trim_ws = TRUE,
show_col_types = FALSE) %>%
dplyr::select(tile_id, time, score) %>%
dplyr::as_tibble()
data$plz <- gsub("_day|.csv", "", filename)
data$plz <- gsub("data/swisscom/", "", data$plz)
return( data )
}
doFuture::registerDoFuture()
future::plan("multisession", workers = 8)
data_day <- plyr::ldply(.data = fs::dir_ls("data/swisscom/",
regexp = "[0-9]_day[.]csv$"),
.fun = read_fun,
.id = NULL,
.parallel = TRUE)Hourly dwell density
read_fun <- function(filename) {
data <- readr::read_delim(filename,
delim = ";", escape_double = FALSE, trim_ws = TRUE,
show_col_types = FALSE) %>%
dplyr::select(tile_id, time, score) %>%
dplyr::as_tibble()
data$plz <- gsub("_hour|.csv", "", filename)
data$plz <- gsub("data/swisscom/", "", data$plz)
return( data )
}
data_hour <- plyr::ldply(.data = fs::dir_ls("data/swisscom/",
regexp = "[0-9]_hour[.]csv$"),
.fun = read_fun,
.id = NULL,
.parallel = TRUE)EDA
Daily
bern_plz_day <- bern_plz %>%
left_join(data_day %>% select(-time))Hourly
bern_plz_hour <- bern_plz %>%
left_join(data_hour)
